def test_provided_means(self):
data = np.random.random((300, 3))
mean = data.mean(axis=0)
pca_spec_mean = pca(data, mean=mean)
pca_calc_mean = pca(data)
np.testing.assert_allclose(mean, pca_calc_mean.mean)
np.testing.assert_allclose(mean, pca_spec_mean.mean)
np.testing.assert_allclose(pca_spec_mean.cov, pca_calc_mean.cov)
def test_api_cs(self):
p = pca(chunksize=1, dim=10)
assert p.chunksize == 1
# in case, we do not have a fixed dimension, pca can not calculate a proper chunksize.
p = pca(chunksize=None)
assert p.chunksize == p._FALLBACK_CHUNKSIZE
p = pca(chunksize=None, dim=10)
assert p.chunksize != 0
assert p.chunksize != p._FALLBACK_CHUNKSIZE
def test_partial_fit(self):
data = [np.random.random((100, 3)), np.random.random((100, 3))]
pca_part = pca()
pca_part.partial_fit(data[0])
pca_part.partial_fit(data[1])
ref = pca(data)
np.testing.assert_allclose(pca_part.mean, ref.mean)
np.testing.assert_allclose(pca_part.eigenvalues, ref.eigenvalues)
np.testing.assert_allclose(pca_part.eigenvectors, ref.eigenvectors)
def test_dimension(self):
assert types.is_int(self.pca_obj.dimension())
# Here:
assert self.pca_obj.dimension() == 1
# Test other variants
obj = pca(data=self.X, dim=-1, var_cutoff=1.0)
assert obj.dimension() == 2
obj = pca(data=self.X, dim=-1, var_cutoff=0.8)
assert obj.dimension() == 1
with self.assertRaises(
ValueError
): # trying to set both dim and subspace_variance is forbidden
pca(data=self.X, dim=1, var_cutoff=0.8)
def test_with_data_in_mem(self):
import pyerna.coordinates as api
data = [
np.random.random((100, 50)),
np.random.random((103, 50)),
np.random.random((33, 50))
]
reader = source(data)
assert isinstance(reader, DataInMemory)
tpca = api.pca(dim=2)
n_centers = 10
km = api.cluster_kmeans(k=n_centers)
disc = api.discretizer(reader, tpca, km)
disc.parametrize()
dtrajs = disc.dtrajs
for dtraj in dtrajs:
n_states = np.max((np.unique(dtraj)))
self.assertGreaterEqual(
n_centers - 1, n_states,
"dtraj has more states than cluster centers")
def test_feature_correlation_MD(self):
# Copying from the test_MD_data
path = pkg_resources.resource_filename(__name__, 'data') + os.path.sep
self.pdb_file = os.path.join(path, 'bpti_ca.pdb')
self.xtc_file = os.path.join(path, 'bpti_mini.xtc')
inp = source(self.xtc_file, top=self.pdb_file)
pcamini = pca(inp)
feature_traj = pcamini.data_producer.get_output()[0]
nfeat = feature_traj.shape[1]
pca_traj = pcamini.get_output()[0]
npcs = pca_traj.shape[1]
test_corr = pcamini.feature_PC_correlation
true_corr = np.corrcoef(feature_traj.T, pca_traj.T)[:nfeat, -npcs:]
np.testing.assert_allclose(test_corr, true_corr, atol=1.E-8)
def test_feature_correlation_data(self):
# Create features with some correlation
feature_traj = np.zeros((100, 3))
feature_traj[:, 0] = np.linspace(-.5, .5, len(feature_traj))
feature_traj[:, 1] = (feature_traj[:, 0] +
np.random.randn(len(feature_traj)) * .5)**1
feature_traj[:, 2] = np.random.randn(len(feature_traj))
nfeat = feature_traj.shape[1]
# PCA
pca_obj = pca(data=feature_traj, dim=3)
pca_traj = pca_obj.get_output()[0]
npcs = pca_traj.shape[1]
# Create correlations
test_corr = pca_obj.feature_PC_correlation
true_corr = np.corrcoef(feature_traj.T, pca_traj.T)[:nfeat, -npcs:]
np.testing.assert_allclose(test_corr, true_corr, atol=1.E-8)
def setUpClass(cls):
import msmtools.generation as msmgen
# set random state, remember old one and set it back in tearDownClass
cls.old_state = np.random.get_state()
np.random.seed(0)
# generate HMM with two Gaussians
cls.P = np.array([[0.99, 0.01], [0.01, 0.99]])
cls.T = 10000
means = [np.array([-1, 1]), np.array([1, -1])]
widths = [np.array([0.3, 2]), np.array([0.3, 2])]
# continuous trajectory
cls.X = np.zeros((cls.T, 2))
# hidden trajectory
dtraj = msmgen.generate_traj(cls.P, cls.T)
for t in range(cls.T):
s = dtraj[t]
cls.X[t, 0] = widths[s][0] * np.random.randn() + means[s][0]
cls.X[t, 1] = widths[s][1] * np.random.randn() + means[s][1]
cls.pca_obj = pca(data=cls.X, dim=1)
def test_variances(self):
obj = pca(data=self.X)
O = obj.get_output()[0]
vars = np.var(O, axis=0)
refs = obj.eigenvalues
assert np.max(np.abs(vars - refs)) < 0.01
